Anirudh Khatry

Anirudh Khatry

Research Fellow at Microsoft PROSE



Anirudh is a Pre-doctoral Research Fellow at Microsoft, working with the PROSE (Program Synthesis) team, based out of Redmond. He primarily works on data wranging techniques using neuro-symbolic approaches. Anirudh is primarily advised by Dr. Ashish Tiwari, Dr. Sumit Gulwani and Dr. Vu Le at Microsoft. He has a bachelor’s degree from Veermata Jijabai Technological Institute (V.J.T.I.) in Information Technology.

Outside of work, Anirudh enjoys playing the guitar and listening to songs.

Download my CV .

  • AI4Code
  • Artificial Intelligence
  • Information Retrieval
  • Program Synthesis
  • Ph.D. in Computer Science, started 2024.

    University of Texas at Austin.

  • B.Tech. in Information Technology, 2017-2021

    Veermata Jijabai Technological Institute, India.

Recent News

All news»

[22/05/2024] I am serving on the PC for ASE-Industry Track 2024.

[05/05/2024] I will be on the PC for OOPSLA ‘24.

[15/04/2024] 🏆 Our paper “Semantically Aligned Question and Code Generation for Automated Insight Generation” is selected as the Best Paper at LLM4Code at ICSE ‘24.

[06/04/2024] 🎓 I will be joining the UToPiA lab at UT Austin in Fall ‘24!

[22/03/2024] Paper on “Semantically Aligned Question and Code Generation for Automated Insight Generation” accepted to LLM4Code at ICSE ‘24.

Recent Publications

Quickly discover relevant content by filtering publications.
(2024). Semantically Aligned Question and Code Generation for Automated Insight Generation (Best Paper). In LLM4Code, ICSE ‘24.


(2023). Alternate Task Technique for Natural Language to Code in Low-Resource Languages.

(2023). COOPER: Learning what to teach models for code generation.

(2023). TSTR: Target Similarity Tuning Meets the Real World. In EMNLP-Findings'23.

PDF Video

(2023). Augmented Embeddings for Custom Retrievals.


(2023). From Words to Code: Harnessing Data for Program Synthesis from Natural Language. In MLAIDS'23.


(2022). Landmarks and Regions: A Robust Approach to Data Extraction. In PLDI'22.



Pre-doctoral Research Fellow
Aug 2022 – Present Redmond
  • Working on incorporation of Natural Language intent into Microsoft products.
Microsoft Research
Research Intern
Jul 2021 – Aug 2022 India
  • Collaborated with Microsoft Edge team for web-based data extraction tasks to improve product purchasing experience.
  • Successfully automated invoice data extraction tasks for the Microsoft IDC Finance team to improve productivity.
  • Employed techniques to combat low-resource name entity recognition tasks by employing ML and program synthesis techniques.
  • Devised Landmark-based Robust Synthesis (LRSyn), a state-of-the-art interpretable data extraction framework, robust to version changes in data.
  • Spearheaded the clustering and landmark detection tasks during the development of LRSyn, and developed a novel fingerprinting technique for images.
  • Successfully published our research paper titled “Landmarks and Regions: A Robust Approach to Data Extraction” at the Conference on Programming Languages Design and Implementation 2022, San Diego.
Human Rights First
Machine Learning Intern
May 2021 – Jul 2021 Remote
  • Collaborated with 30 changemakers to develop a war-crime detection tool using social media channels.
  • Fine-tuned a distil-RoBERTa model for binary classification of war crimes
  • Spearheaded the development of a novel two stage prediction pipeline for multi-label classification of warcrimes.
Samsung Research and Development Institute, India
Research Intern
May 2020 – Jul 2020 Remote
  • Worked with the On-Device AI team to improve system performance using Reinforcement Learning.
  • Built a State-Of-The-Art Multi-Agent Deep Q-network leveraging prioritized experience replay(PER) and time-bound dynamic reward functions
  • Designed a landmark agent simulation environment to show proof of concept.
Pexabyte Technology Solutions Pvt. Ltd.
Programming Analyst Intern
May 2019 – Jul 2019 Remote
  • Coordinated with the product development team to build an ERP application for manufacturing and service-based industries.
  • Employed JavaFX for the development of the application and MySQL for database management.
  • Followed an agile based product development life cycle with constant interaction with key product owners.


Neural Networks and Deep Learning
See certificate
Blockchain Fundamentals
See certificate
Fundamentals of Reinforcement Learning
See certificate
Introduction to Quantum Computing